def hypothesis4Testing(numOfFiles, *timeSeriesFileNames):
if len(timeSeriesFileNames) != numOfFiles:
print "Number of files mentioned do not match the specified files provided"
return
csvDataList = []
for fileName in timeSeriesFileNames:
with open(fileName, 'rb') as f:
reader = csv.reader(f)
csvData = map(tuple, reader)
csvDataList.append(csvData)
testData= []
for i in csvDataList:
td= getColumnFromListOfTuples(i,2)
testData.append(convertListToFloat(td))
#print "testData" + str(testData)
avgTimeSeries=findAverageTimeSeries(testData)
#print "Average Time Series :::::: "+ str(avgTimeSeries)
#Finding anomaly dates for every time series with average time series
count=0
tcases=0
h4res=[]
for i in testData:
#print "Value of i ::::::::::::::::::::::::: "+ str(count)
#ser = findDiffSeries(i,1)
#print "Result of Ser::::::::::::::::"+ str(ser)
#(r,s)=MADThreshold(ser)
#print "Result of MAD TEST :::::::::::::::::::::::::"+ str(r)+ ":::"+str(s)
#p =[x for x in ser if x > 100 or x < -100]
#print "Exception list :::::::::::"+ str(p)
#print "length of exception list ::::::::::::::"+ str(len(p))
#plt.plot(ser)
#plt.show()
temp= slopeCurveBasedDetection(i,avgTimeSeries,1)
#temp= slopeBasedDetection(i,True,avgTimeSeries,True,7,True,0,0)
tcases=tcases+len(temp)
#print "TEMP :::::::::::::::::::::::::::::::::::::::::::::"+ str(csvDataList[count])
res= anomalyDatesSlopeBaseddetetion(temp,csvDataList[count])
h4res.append( (count,res))
#h4res.append( (count,temp))
count=count+1
#print "Final Result ::::::::::::::::"+ str(h4res)
mergeDates(h4res[0][1])
print "Final Reported Anomalies ::::::::::::::::::: "+ str(tcases)
def hypothesis4Testing(numOfFiles, *timeSeriesFileNames):
if len(timeSeriesFileNames) != numOfFiles:
print "Number of files mentioned do not match the specified files provided"
return
csvDataList = [] # 2D list storing data of each file
for fileName in timeSeriesFileNames:
with open(fileName, "rb") as f:
reader = csv.reader(f)
csvData = map(tuple, reader)
csvDataList.append(csvData)
centresList = []
testData = []
temp1 = []
for i in csvDataList:
td = getColumnFromListOfTuples(i, 2) # wholesale price, indexing starts from 1
testData.append(convertListToFloat(td))
temp1 = getColumnFromListOfTuples(i, 0)
temp2 = getColumnFromListOfTuples(i, 2)
temp = zip(temp1, temp2)
centresList.append(temp)
# print "testData" + str(testData)
avgTimeSeries = findAverageTimeSeries(testData)
avgTimeSeries = zip(temp1, avgTimeSeries)
# print "Average Time Series :::::: "+ str(avgTimeSeries)
for i, c_list in enumerate(centresList):
# CALL SLOPE BASED
slopeBasedResult = slopeBased(c_list, False, avgTimeSeries, False)
slopeBasedResult = mergeDates(slopeBasedResult)
# Correlation
correlationResult = anomaliesFromWindowCorrelationWithConstantlag(c_list, avgTimeSeries)
correlationResult = mergeDates(correlationResult)
# Linear Regression
lrResult = linear_regression(avgTimeSeries, c_list, 1)
lrResult = mergeDates(lrResult)
result = intersection(
3, slopeBasedResult, "slope_based", correlationResult, "correlation", lrResult, "linear_regression"
)
print "Anomalies fior time-series " + str(i) + " are:"
for (a, b, c) in result:
print str(a) + "," + str(b) + "," + str(c)
